{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UVZKDAHOXZRQ6DIJ4GYMYQU2FA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c08f909e3eb7ba9d4518f823275984ff4aa05513514306734a65cf56cffdf58d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T18:46:56Z","title_canon_sha256":"483cc36cb366f65344686c123a026b4468752615d4ccfdd4875583dbd8d6e703"},"schema_version":"1.0","source":{"id":"2601.18778","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.18778","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"arxiv_version","alias_value":"2601.18778v3","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18778","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"pith_short_12","alias_value":"UVZKDAHOXZRQ","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"pith_short_16","alias_value":"UVZKDAHOXZRQ6DIJ","created_at":"2026-07-01T01:18:24Z"},{"alias_kind":"pith_short_8","alias_value":"UVZKDAHO","created_at":"2026-07-01T01:18:24Z"}],"graph_snapshots":[{"event_id":"sha256:6e531b828b0c13506be57f8b9165ad4f04d7cb4857416ca69d4c980c40758549","target":"graph","created_at":"2026-07-01T01:18:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.18778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental question: Can a pretrained LLM leverage latent knowledge to generate an automated curriculum for problems it cannot solve? We explore this with SOAR: An asymmetric self-play framework that uses meta-RL to surface these pedagogical signals. A teacher model proposes synthetic problems for a student model, and is rewarded with its improvement on a subset of hard problems, thus grounding the curriculum in real student progress rather than int","authors_text":"Ariel Kwiatkowski, John Quan, Julia Kempe, Kartik Ahuja, Shobhita Sundaram, Yann Ollivier","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T18:46:56Z","title":"Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18778","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d85d3b4dc52e1255dffd9c74e6110702e1bbb1179ed41190db04b43c5913f5ca","target":"record","created_at":"2026-07-01T01:18:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c08f909e3eb7ba9d4518f823275984ff4aa05513514306734a65cf56cffdf58d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T18:46:56Z","title_canon_sha256":"483cc36cb366f65344686c123a026b4468752615d4ccfdd4875583dbd8d6e703"},"schema_version":"1.0","source":{"id":"2601.18778","kind":"arxiv","version":3}},"canonical_sha256":"a572a180eebe630f0d09e1b0cc429a283d324363f09492459bb6e1b0308d570f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a572a180eebe630f0d09e1b0cc429a283d324363f09492459bb6e1b0308d570f","first_computed_at":"2026-07-01T01:18:24.161911Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:24.161911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p7NDKaiJ0bnzpHuZTy+K9jvoNgAJh/o9/ayWmOrnEz0SOCHJxb8fKFe0DztLtbaUG+//3gWdWF85ge7FC/Q1Dg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:24.162343Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.18778","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d85d3b4dc52e1255dffd9c74e6110702e1bbb1179ed41190db04b43c5913f5ca","sha256:6e531b828b0c13506be57f8b9165ad4f04d7cb4857416ca69d4c980c40758549"],"state_sha256":"1c7d507d41ff21d912daf6b93e909a7a8f4f97cdbfa2db5c964797d26c91d14d"}